INDEX

Explanations

terms related to biological processes and their interactions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

ending in "ations", "ating", "logies" or "ative"

np_acts-logits-general · gemini-2.0-flash

-ation, -ation, -ation, -ation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ation

-1.91

ity

-1.31

logy

-1.24

ment

-1.15

ATION

-1.04

ology

-1.02

ism

-1.00

ction

-0.95

hip

-0.91

ness

-0.89

POSITIVE LOGITS

hips

1.02

nesses

0.83

ations

0.79

ments

0.79

ATIONS

0.67

^(@)

0.67

$_['

0.66

 latter

0.65

pausal

0.64

."</

0.64

Activations Density 0.934%

terms related to biological processes and their interactions

ending in "ations", "ating", "logies" or "ative"

-ation, -ation, -ation, -ation

No Comments

No Known Activations